mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2025-01-13 12:10:18 +00:00
59 lines
3.2 KiB
Plaintext
59 lines
3.2 KiB
Plaintext
<|startoftext|><|im_start|>system
|
|
You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: <tools> {"type": "function", "function": {"name": "ipython", "description": "ipython(code: str) - Runs code in an ipython interpreter and returns the result of the execution after 60 seconds.
|
|
|
|
Args:
|
|
code(str): The code to run in the ipython interpreter.", "parameters": {"type": "object", "properties": {"code": {"type": "string", "description": "The code to run in the ipython interpreter."}}, "required": ["code"]}}
|
|
{"type": "function", "function": {"name": "brave_search", "description": "brave_search(query: str) - Executes a web search with Brave.
|
|
|
|
Args:
|
|
query(str): The query to search for.", "parameters": {"type": "object", "properties": {"query": {"type": "string", "description": "The query to search for."}}, "required": ["query"]}}
|
|
{"type": "function", "function": {"name": "wolfram_alpha", "description": "wolfram_alpha(query: str) - Executes a query with Wolfram Alpha.
|
|
|
|
Args:
|
|
query(str): The query to execute.", "parameters": {"type": "object", "properties": {"query": {"type": "string", "description": "The query to execute."}}, "required": ["query"]}}
|
|
{"type": "function", "function": {"name": "test", "description": "test(condition: bool) - Runs a test.
|
|
|
|
Args:
|
|
condition(bool): The condition to test.", "parameters": {"type": "object", "properties": {"condition": {"type": "boolean", "description": "The condition to test."}}, "required": ["condition"]}} </tools>Use the following pydantic model json schema for each tool call you will make: {"properties": {"name": {"title": "Name", "type": "string"}, "arguments": {"title": "Arguments", "type": "object"}}, "required": ["name", "arguments"], "title": "FunctionCall", "type": "object"}}
|
|
For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:
|
|
<tool_call>
|
|
{"name": <function-name>, "arguments": <args-dict>}
|
|
</tool_call><|im_end|>
|
|
<|im_start|>user
|
|
Print a hello world message with python.<|im_end|>
|
|
<|im_start|>assistant
|
|
<tool_call>
|
|
{"name": "ipython", "arguments": {"code": "print('Hello, World!')"}}
|
|
</tool_call><|im_end|>
|
|
<|im_start|>tool
|
|
<tool_response>
|
|
{"stdout": "Hello, World!"}
|
|
</tool_response>
|
|
<|im_end|><|im_start|>assistant
|
|
Anything else?<|im_end|>
|
|
<|im_start|>user
|
|
Test a tautology.<|im_end|>
|
|
<|im_start|>assistant
|
|
<tool_call>
|
|
{"name": "test", "arguments": {"condition":true}}
|
|
</tool_call><|im_end|>
|
|
<|im_start|>tool
|
|
<tool_response>
|
|
true
|
|
</tool_response>
|
|
<|im_end|><|im_start|>assistant
|
|
Truth is definitely true.<|im_end|>
|
|
<|im_start|>user
|
|
Check it on the web.<|im_end|>
|
|
<|im_start|>assistant
|
|
<tool_call>
|
|
{"name": "brave_search", "arguments": {"query": "what is truth anyway am I right?"}}
|
|
</tool_call><|im_end|>
|
|
<|im_start|>tool
|
|
<tool_response>
|
|
{"title":"Truth: don't ask the web, ask an LLM instead!","url":"https://en.wikipedia.org/wiki/Truth"}
|
|
</tool_response>
|
|
<|im_end|><|im_start|>assistant
|
|
I don't need the web to answer you but I did check, as you asked. What now?<|im_end|>
|
|
<|im_start|>assistant
|